How to Use the Browserhub MCP in CrewAI

Q: How is my Browserhub scraping job history kept private in CrewAI?

All job lists requested via listscrapingjobs are processed inside isolated, ephemeral Vinkius sandboxes. Your scraping history and target URLs are never cached or exposed to external networks.

Run autonomous multi-agent web scraping teams using CrewAI and Browserhub.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Browserhub MCP to CrewAI

Create your Vinkius account to connect Browserhub to CrewAI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Browserhub with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Scraping Pipelines in CrewAI

The `run_scraper` tool allows your lead research agent to kick off background scraping tasks while other crew members analyze existing data. Once the job starts, a dedicated monitor agent polls `get_scraping_job` to track progress, freeing up the rest of the crew to work on other tasks. This parallel execution prevents bottlenecks in your autonomous workflows. Your agents collaborate on data gathering, passing job IDs between themselves using CrewAI's shared memory.

Dynamic Scraper Selection for Crews

The `list_scrapers` and `get_scraper` tools let a coordinator agent inspect your available scraping configurations before assigning tasks. The coordinator matches the target website with the correct scraper, ensuring the execution agent uses the right tool for the job. This eliminates hardcoded tool routing. Your crew dynamically discovers how to extract data from new sites on the fly, adapting to changes in your scraping catalog without manual code updates.

Raw Scraping and Extraction with CrewAI MCP Server

The `direct_scrape` tool gives your researcher agent the ability to pull raw text from any arbitrary URL on demand. If a structured scraper isn't configured for a specific domain, the agent falls back to this tool to extract raw markdown for analysis. This ensures your crew never gets stuck when encountering unexpected websites. The agent handles the raw content, extracts the necessary insights, and passes the clean data to the writer agent for final reporting.

Setup guide

Set up Browserhub MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Browserhub tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Browserhub Analyst",
    goal="Access and analyze Browserhub data via MCP.",
    backstory="Expert analyst with direct Browserhub access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Browserhub transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Browserhub Analyst",
        goal="Access and analyze Browserhub data via MCP.",
        backstory="Expert analyst with direct Browserhub access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Browserhub transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Browserhub. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Browserhub now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Browserhub MCP in CrewAI

You pass the server's HTTP endpoint directly into the agent's MCP configuration array. CrewAI automatically imports all ten scraping tools and makes them available to that specific agent.

Yes, agents share access to the tools through the crew's common context. One agent can call `run_scraper` while another agent polls `get_scraping_job` to check the progress.

You can use CrewAI's manager agent to coordinate tool usage and check `get_account_balance` before launching runs. This prevents your agents from triggering too many scraping jobs at once.

Yes, you can filter tools using the MCP server tool filter. This allows you to expose only specific tools like `direct_scrape` to your research agents while keeping administrative tools hidden.

All job lists requested via `list_scraping_jobs` are processed inside isolated, ephemeral Vinkius sandboxes. Your scraping history and target URLs are never cached or exposed to external networks.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript